Heart Attack Analysis-EDA

Statsly Analytics

By Moumita Das

Problem Statement

Within these data, lies important patterns and variables. Find out some interesting insights from the data provided.

Importing all libraries

import pandas as pd # for reading the file
import numpy as np # for numericals & mathematicals experssion
import seaborn as sns # for data visulization
import matplotlib.pyplot as plt # for data visulization
%matplotlib inline 
import time 
import warnings
warnings.filterwarnings('ignore')

pip install pandas-profiling

Requirement already satisfied: pandas-profiling in c:\users\dell\anaconda3\lib\site-packages (3.1.0)
Requirement already satisfied: htmlmin>=0.1.12 in c:\users\dell\anaconda3\lib\site-packages (from pandas-profiling) (0.1.12)
Requirement already satisfied: seaborn>=0.10.1 in c:\users\dell\anaconda3\lib\site-packages (from pandas-profiling) (0.11.2)
Requirement already satisfied: pydantic>=1.8.1 in c:\users\dell\anaconda3\lib\site-packages (from pandas-profiling) (1.8.2)
Requirement already satisfied: scipy>=1.4.1 in c:\users\dell\anaconda3\lib\site-packages (from pandas-profiling) (1.7.1)
Requirement already satisfied: joblib~=1.0.1 in c:\users\dell\anaconda3\lib\site-packages (from pandas-profiling) (1.0.1)
Requirement already satisfied: matplotlib>=3.2.0 in c:\users\dell\anaconda3\lib\site-packages (from pandas-profiling) (3.4.3)
Requirement already satisfied: tangled-up-in-unicode==0.1.0 in c:\users\dell\anaconda3\lib\site-packages (from pandas-profiling) (0.1.0)
Requirement already satisfied: requests>=2.24.0 in c:\users\dell\anaconda3\lib\site-packages (from pandas-profiling) (2.26.0)
Requirement already satisfied: phik>=0.11.1 in c:\users\dell\anaconda3\lib\site-packages (from pandas-profiling) (0.12.0)
Requirement already satisfied: markupsafe~=2.0.1 in c:\users\dell\anaconda3\lib\site-packages (from pandas-profiling) (2.0.1)
Requirement already satisfied: pandas!=1.0.0,!=1.0.1,!=1.0.2,!=1.1.0,>=0.25.3 in c:\users\dell\anaconda3\lib\site-packages (from pandas-profiling) (1.3.4)
Requirement already satisfied: numpy>=1.16.0 in c:\users\dell\anaconda3\lib\site-packages (from pandas-profiling) (1.20.3)
Requirement already satisfied: missingno>=0.4.2 in c:\users\dell\anaconda3\lib\site-packages (from pandas-profiling) (0.5.0)
Requirement already satisfied: jinja2>=2.11.1 in c:\users\dell\anaconda3\lib\site-packages (from pandas-profiling) (2.11.3)
Requirement already satisfied: tqdm>=4.48.2 in c:\users\dell\anaconda3\lib\site-packages (from pandas-profiling) (4.62.3)
Requirement already satisfied: multimethod>=1.4 in c:\users\dell\anaconda3\lib\site-packages (from pandas-profiling) (1.6)
Requirement already satisfied: visions[type_image_path]==0.7.4 in c:\users\dell\anaconda3\lib\site-packages (from pandas-profiling) (0.7.4)
Requirement already satisfied: PyYAML>=5.0.0 in c:\users\dell\anaconda3\lib\site-packages (from pandas-profiling) (6.0)
Requirement already satisfied: attrs>=19.3.0 in c:\users\dell\anaconda3\lib\site-packages (from visions[type_image_path]==0.7.4->pandas-profiling) (21.2.0)
Requirement already satisfied: networkx>=2.4 in c:\users\dell\anaconda3\lib\site-packages (from visions[type_image_path]==0.7.4->pandas-profiling) (2.6.3)
Requirement already satisfied: imagehash in c:\users\dell\anaconda3\lib\site-packages (from visions[type_image_path]==0.7.4->pandas-profiling) (4.2.1)
Requirement already satisfied: Pillow in c:\users\dell\anaconda3\lib\site-packages (from visions[type_image_path]==0.7.4->pandas-profiling) (8.4.0)
Requirement already satisfied: pyparsing>=2.2.1 in c:\users\dell\anaconda3\lib\site-packages (from matplotlib>=3.2.0->pandas-profiling) (3.0.4)
Requirement already satisfied: python-dateutil>=2.7 in c:\users\dell\anaconda3\lib\site-packages (from matplotlib>=3.2.0->pandas-profiling) (2.8.2)
Requirement already satisfied: cycler>=0.10 in c:\users\dell\anaconda3\lib\site-packages (from matplotlib>=3.2.0->pandas-profiling) (0.10.0)
Requirement already satisfied: kiwisolver>=1.0.1 in c:\users\dell\anaconda3\lib\site-packages (from matplotlib>=3.2.0->pandas-profiling) (1.3.1)
Requirement already satisfied: six in c:\users\dell\anaconda3\lib\site-packages (from cycler>=0.10->matplotlib>=3.2.0->pandas-profiling) (1.16.0)
Requirement already satisfied: pytz>=2017.3 in c:\users\dell\anaconda3\lib\site-packages (from pandas!=1.0.0,!=1.0.1,!=1.0.2,!=1.1.0,>=0.25.3->pandas-profiling) (2021.3)
Requirement already satisfied: typing-extensions>=3.7.4.3 in c:\users\dell\anaconda3\lib\site-packages (from pydantic>=1.8.1->pandas-profiling) (3.10.0.2)
Requirement already satisfied: certifi>=2017.4.17 in c:\users\dell\anaconda3\lib\site-packages (from requests>=2.24.0->pandas-profiling) (2021.10.8)
Requirement already satisfied: charset-normalizer~=2.0.0 in c:\users\dell\anaconda3\lib\site-packages (from requests>=2.24.0->pandas-profiling) (2.0.4)
Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\users\dell\anaconda3\lib\site-packages (from requests>=2.24.0->pandas-profiling) (1.26.7)
Requirement already satisfied: idna<4,>=2.5 in c:\users\dell\anaconda3\lib\site-packages (from requests>=2.24.0->pandas-profiling) (3.2)
Requirement already satisfied: colorama in c:\users\dell\anaconda3\lib\site-packages (from tqdm>=4.48.2->pandas-profiling) (0.4.4)
Requirement already satisfied: PyWavelets in c:\users\dell\anaconda3\lib\site-packages (from imagehash->visions[type_image_path]==0.7.4->pandas-profiling) (1.1.1)
Note: you may need to restart the kernel to use updated packages.

Loading Dataset

data = pd.read_csv("Heart_Attack_Analysis_task4.csv")

from pandas_profiling import ProfileReport
profile = ProfileReport(data, title="Pandas Profiling Report")

profile

• We observe that there is one duplicate row in our data set. So lets drop this row!

data.isnull().describe()

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	caa	thall	output
count	303	303	303	303	303	303	303	303	303	303	303	303	303	303
unique	1	1	1	1	1	1	1	1	1	1	1	1	1	1
top	False	False	False	False	False	False	False	False	False	False	False	False	False	False
freq	303	303	303	303	303	303	303	303	303	303	303	303	303	303

data.drop_duplicates(inplace=True)
data.reset_index(drop=True, inplace=True)
data.shape

(302, 14)

fig, ax = plt.subplots(ncols = 2, nrows = 7, figsize = (27, 60))
index = 0
ax = ax.flatten()

for cols, value in data.items():
    if cols != 'type':
        sns.boxplot(y=cols,data = data,ax=ax[index])
        index += 1
    
plt.tight_layout(pad = 0.5, w_pad = 0.7, h_pad = 5.0)
plt.show()

# chol outlier - 85 index value
data[data['chol']>390]

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	caa	thall	output
28	65	0	2	140	417	1	0	157	0	0.8	2	1	2	1
85	67	0	2	115	564	0	0	160	0	1.6	1	0	3	1
96	62	0	0	140	394	0	0	157	0	1.2	1	0	2	1
219	63	0	0	150	407	0	0	154	0	4.0	1	3	3	0
245	56	0	0	134	409	0	0	150	1	1.9	1	2	3	0

# thalachh outlier - 271 index value
data[data["thalachh"]<80]

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	caa	thall	output
271	67	1	0	120	237	0	1	71	0	1.0	1	0	2	0

# oldpeak outlier - 203, 220 index value
data[data["oldpeak"]>5]

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	caa	thall	output
203	62	0	0	160	164	0	0	145	0	6.2	0	3	3	0
220	55	1	0	140	217	0	1	111	1	5.6	0	0	3	0

data.drop(data.index[[85,203,220,271]], inplace = True)

data.shape

(299, 14)

fig, ax = plt.subplots(ncols = 2, nrows = 7, figsize = (27, 60))
index = 0
ax = ax.flatten()

for col, value in data.items():
    if col != 'type':
        sns.distplot(value, ax = ax[index])
        index += 1
plt.tight_layout(pad = 0.5, w_pad = 0.7, h_pad = 5.0)

sns.set_style('darkgrid')
sns.distplot(data['age'],bins=30,kde=True)
plt.title('Age Distribution of Patients',size=15)
plt.xlabel('Age',size=12);

• We see that the Age Distribution of Patients is roughly normal

The output column is our target column.Let's divide the dataset into numerical and categorical columns.

numerical_cols = ['age', 'trtbps', 'chol', 'thalach', 'oldpeak']
categorical_cols = ['sex', 'cp', 'caa', 'fbs', 'restecg', 'exng', 'slp', 'thall']
target = ['output']

plt.figure(figsize=(12,6))
sns.set(font_scale=1.4)
sns.set_style('whitegrid')
sns.countplot(x='output', data=data, palette='magma').set(xlabel="Output")
plt.title("Countplot of People with less or more chance of heart attack")

Text(0.5, 1.0, 'Countplot of People with less or more chance of heart attack')

print("Number of people with more chance of heart attack:", data[data["output"]==1].value_counts().sum())
print("Number of people with less chance of heart attack:",data[data["output"]==0].value_counts().sum())

Number of people with more chance of heart attack: 164
Number of people with less chance of heart attack: 135

• 54.69% of the total people have more chance of heart attack and 45.30% people have less chance of a heart attack.

sns.countplot(x='sex', data=data, palette='magma')
plt.title("Countplot of Sex")

Text(0.5, 1.0, 'Countplot of Sex')

print("Number of people with sex labelled as 1:", data[data["sex"]==1].value_counts().sum())
print("Number of people with sex labelled as 0:",data[data["sex"]==0].value_counts().sum())

Number of people with sex labelled as 1: 204
Number of people with sex labelled as 0: 94

• 68.45% belong to the sex = 1 and 31.54% belong to the sex = 0

fig, ax = plt.subplots(2,3, figsize=(20,18))
sns.countplot(x='fbs', data=data, palette='magma', ax=ax[0][0]).set(title='Fasting Blood Sugar')
sns.countplot(x='exng', data=data, palette='magma', ax=ax[0][1]).set(title='Exercise Induced Angina')
sns.countplot(x='restecg', data=data, palette='magma', ax=ax[1][0]).set(title='Rest ECG')
sns.countplot(x='cp', data=data, palette='magma', ax=ax[0][2]).set(title='Chest Pain Type')
sns.countplot(x='caa', data=data, palette='magma', ax=ax[1][1]).set(title='Number of major vessels')
sns.countplot(x='thall', data=data, palette='magma', ax=ax[1][2]).set(title='Thallium Stress Test')

[Text(0.5, 1.0, 'Thallium Stress Test')]

• More than 32% of the people have Exercise Induced Angina
• 47% of the people have Typical Angina or Chest Pain Type 1 and 28% have Non Anginal Pain.
• 48% of the people have Normal Rest ECG while 50% of the people have ST-T wave abnormality.
• More than 54% of the people have Thalium Stress test value of 2

fig, ax = plt.subplots(2,2, figsize=(20,18))
sns.histplot(x=data["age"], ax=ax[0][0], color="blue", kde=True).set(title='Age')
sns.histplot(x=data["trtbps"], ax=ax[0][1], color="blue", kde=True).set(title='Resting Blood Pressure')
sns.histplot(x=data["chol"], ax=ax[1][0], color="green", kde=True).set(title='Cholestrol Levels')
sns.histplot(x=data["thalachh"], ax=ax[1][1], color="green", kde=True).set(title='Maximum Heart Rate Achieved')

[Text(0.5, 1.0, 'Maximum Heart Rate Achieved')]

• Most of the people in this dataset have an age between 40 and 70.
• There are a large number of people who have blood pressure in the range of 120 and 150. 90/60mmHg-120/80mmHg is considered as the ideal blood pressure for a healthy person. High blood pressure is considered to be 140/90mmHg or higher.
• Many people who have cholestrol levels in the range of 200-300mg/dL. Total cholesterol levels less than 200 milligrams per deciliter (mg/dL) are considered desirable for adults.
• Many people have Max Heart Rate in the range of 140 and 160 bpms.According to American Heart Association the Maximum Heart Rate is around 220 beats per minute (bpm) minus the person's age.

sns.countplot(x='output',data=data,palette='muted',hue='cp')
plt.title('Number of No Heart Attacks vs. Heart Attacks by Chest Pain type',size=13)
plt.xlabel('Patients',size=12)
plt.ylabel('Count',size=12);

• There are four types of chest pains.
• Chest pain type 0 had less heart attack occurences. It also had the most patients with no heart attacks.
• Chest pain type 1 had more heart attack occurences.
• Chest pain type 2 also had more heart attack occurences. It also had the most heart attack occurences.
• Chest pain type 3 also had more heart attack occurences. It also had the least heart attack occurences.

data.corr()

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	caa	thall	output
age	1.000000	-0.088817	-0.061404	0.290154	0.199493	0.125787	-0.110029	-0.393208	0.102705	0.204387	-0.155231	0.308477	0.059918	-0.220631
sex	-0.088817	1.000000	-0.047904	-0.054817	-0.186256	0.044262	-0.075261	-0.034871	0.137000	0.122017	-0.041790	0.126330	0.224448	-0.284103
cp	-0.061404	-0.047904	1.000000	0.054810	-0.108550	0.094171	0.047954	0.284079	-0.395201	-0.131025	0.105434	-0.193687	-0.160748	0.424523
trtbps	0.290154	-0.054817	0.054810	1.000000	0.166258	0.180277	-0.114064	-0.052007	0.067141	0.177908	-0.113409	0.085949	0.058252	-0.140193
chol	0.199493	-0.186256	-0.108550	0.166258	1.000000	0.018035	-0.140873	-0.022853	0.083189	0.081133	-0.003168	0.121369	0.088353	-0.117504
fbs	0.125787	0.044262	0.094171	0.180277	0.018035	1.000000	-0.083970	-0.014381	0.023966	0.018019	-0.068208	0.146917	-0.028985	-0.030389
restecg	-0.110029	-0.075261	0.047954	-0.114064	-0.140873	-0.083970	1.000000	0.059180	-0.076541	-0.055173	0.091684	-0.074963	-0.004903	0.142710
thalachh	-0.393208	-0.034871	0.284079	-0.052007	-0.022853	-0.014381	0.059180	1.000000	-0.388779	-0.347358	0.380415	-0.246724	-0.098417	0.412548
exng	0.102705	0.137000	-0.395201	0.067141	0.083189	0.023966	-0.076541	-0.388779	1.000000	0.299410	-0.260003	0.132958	0.207123	-0.439143
oldpeak	0.204387	0.122017	-0.131025	0.177908	0.081133	0.018019	-0.055173	-0.347358	0.299410	1.000000	-0.555496	0.229898	0.188596	-0.429426
slp	-0.155231	-0.041790	0.105434	-0.113409	-0.003168	-0.068208	0.091684	0.380415	-0.260003	-0.555496	1.000000	-0.086155	-0.087206	0.335765
caa	0.308477	0.126330	-0.193687	0.085949	0.121369	0.146917	-0.074963	-0.246724	0.132958	0.229898	-0.086155	1.000000	0.158570	-0.411355
thall	0.059918	0.224448	-0.160748	0.058252	0.088353	-0.028985	-0.004903	-0.098417	0.207123	0.188596	-0.087206	0.158570	1.000000	-0.345042
output	-0.220631	-0.284103	0.424523	-0.140193	-0.117504	-0.030389	0.142710	0.412548	-0.439143	-0.429426	0.335765	-0.411355	-0.345042	1.000000

plt.figure(figsize = (35,15))
plt.title('Correlation of all the Columns', fontsize = 20)
sns.heatmap(data.corr(), annot = True, vmin = -1, vmax = 1, center = 0, fmt = '.1g', linewidths = 1, linecolor = 'white', 
            square = True, cmap ='RdBu')

<AxesSubplot:title={'center':'Correlation of all the Columns'}>

Output related to different attributes

fig, ax = plt.subplots(2,3, figsize=(22,18))
sns.kdeplot(x="age", data=data, hue="output", ax=ax[0][0], fill="True", palette="magma").set(title="Heart Attack related to Age")
sns.kdeplot(x="cp", data=data, hue="output", ax=ax[0][1], fill="True", palette="viridis").set(title="Heart Attack related to Chest Pain Types")
sns.kdeplot(x="thalachh", data=data, hue="output", ax=ax[1][0], fill="True", palette="viridis").set(title="Heart Attack related to Heart Rate")
sns.kdeplot(x="chol", data=data, hue="output", ax=ax[1][1], fill="True", palette="magma").set(title="Heart Attack related to Cholestrol")
sns.kdeplot(x="thall", data=data, hue="output", ax=ax[0][2], fill="True", palette="magma").set(title="Heart Attack related to Thallium Stress Test")
sns.kdeplot(x="trtbps", data=data, hue="output", ax=ax[1][2], fill="True", palette="viridis").set(title="Heart Attack related to Blood Pressure")

[Text(0.5, 1.0, 'Heart Attack related to Blood Pressure')]

• Most people that suffer heart attacks lie in the age of 40-60 Years
• People that have heart attacks often suffer from Non Anginal Pain or Type 2 Chest Pain.
• Large number of people who suffer heart attacks have Max heart rates between 140-180
• People with Cholestrol Levels higher than 200mg/dL tend to have heart attacks more.
• Heart Attacks were seen in people with Thallium Stress Text value of 2

fig, ax = plt.subplots(2,2, figsize=(18, 15))
sns.boxplot(x="thall", y="thalachh", data=data, palette="magma", ax=ax[0][0]).set(title="Thallium Stress Test vs Max Heart Rate")
sns.boxplot(x="thall", y="trtbps", data=data, palette="viridis", ax=ax[0][1]).set(title="Thallium Stress Test vs Resting Blood Pressure")
sns.boxplot(x="thall", y="chol", data=data, palette="viridis", ax=ax[1][0]).set(title="Chest Pain Type vs Age")
sns.boxplot(x="cp", y="age", data=data, palette="magma", ax=ax[1][1]).set(title="Chest Pain Type vs Age")

[Text(0.5, 1.0, 'Chest Pain Type vs Age')]

• There are significant outliers in the categorical data.
• A significant number of people with Thallium Stress Test Value of 2 have higher Max Heart Rates.
• Some people with Thallium Stress Test Value of 1 have higher Resting Blood Pressure.
• People with Thallium Stress Test values off 2 and 3 tend to have higher cholestrol levels.
• People with age of more than 50 years tend to have Anginal Pains.